© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 79845
    Prev
    Next
    INDEX
    Explanations

    inventory management

    np_acts-logits-general · gemini-2.5-flash-lite

    Explanation of neuron 4 behavior: the main thing this neuron does is find occurrences of the capitalized word “Inventory.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    2
    -3.98
    3
    -3.88
    er
    -3.84
    9
    -3.59
    1
    -3.59
    8
    -3.47
    7
    -3.39
    (
    -3.38
    L
    -3.38
    0
    -3.25
    POSITIVE LOGITS
    ᠁
    2.86
    媖
    2.81
    🕗
    2.80
    芣
    2.73
    踅
    2.66
     implementar
    2.58
    禿
    2.48
    五三
    2.41
    趼
    2.36
    のための
    2.34
    Activations Density 0.005%

    No Known Activations